iterate to unify the fastq validation and stats

TORCH-Consortium · Jun 22, 2024 · 3d63947 · 3d63947
1 parent af0b380
commit 3d63947
Show file tree

Hide file tree

Showing 5 changed files with 15 additions and 14 deletions.
diff --git a/bin/fastq_cohort_validation.py b/bin/fastq_cohort_validation.py
@@ -18,7 +18,7 @@
     vcf_name = args['joint_vcf_name']
 
     # Check for files matching *check.passed*
-    passed_files = glob.glob("*check.passed*")
+    passed_files = glob.glob("fastq_validation/*check.passed*")
     if passed_files:
         with open(f"{vcf_name}.fastqs.passed.tsv", "w") as outfile:
             for fname in passed_files:
@@ -31,7 +31,7 @@
     open(f"{vcf_name}.fastqs.failed.tsv", 'a').close()
 
     # Check for files matching *check.failed*
-    failed_files = glob.glob("*check.failed*")
+    failed_files = glob.glob("fastq_validation/*check.failed*")
     if failed_files:
         with open(f"{vcf_name}.fastqs.failed.tsv", "w") as outfile:
             for fname in failed_files:

diff --git a/modules/fastq_utils/validator.nf b/modules/fastq_utils/validator.nf
@@ -14,7 +14,7 @@ process FASTQ_VALIDATOR {
     output:
         tuple val(sampleName), path("*.check.*tsv")
         path("*.check.*tsv")                          , emit: check_result
-        tuple val(sampleName), path(sampleReads)      , emit: passed_reads
+        tuple val(sampleName), path(sampleReads)      , emit: reads
 
     shell:
 

diff --git a/modules/utils/fastq_cohort_validation.nf b/modules/utils/fastq_cohort_validation.nf
@@ -3,7 +3,8 @@ process UTILS_FASTQ_COHORT_VALIDATION {
     publishDir params.results_dir, mode: params.save_mode, enabled: params.should_publish
 
     input:
-        path("*")
+        path("fastq_validation/*")
+        path("fastq_stats/*")
 
     output:
         path("*.fastqs.passed.tsv"), emit: passed_fastqs

diff --git a/modules/utils/fastq_stats.nf b/modules/utils/fastq_stats.nf
@@ -10,15 +10,15 @@ process UTILS_FASTQ_STATS {
         path("*fastq_stats.csv")
 
     script:
-       
-        """
-        seqkit stats -a -T  *fastq*  > ${sampleName}.seqkit.txt
+
+    """
+    seqkit stats -a -T  *fastq*  > ${sampleName}.seqkit.txt
         cat ${sampleName}.seqkit.txt | csvtk space2tab | csvtk tab2csv > ${sampleName}.seqkit_stats.final.csv
 
-        md5sum *fastq* > ${sampleName}.md5sum.txt 
+        md5sum *fastq* > ${sampleName}.md5sum.txt
         cat ${sampleName}.md5sum.txt | csvtk space2tab | csvtk tab2csv | csvtk add-header -n md5sum,file > ${sampleName}.md5sum_stats.csv
 
-        du -shL *fastq* > ${sampleName}.du.txt 
+        du -shL *fastq* > ${sampleName}.du.txt
         cat ${sampleName}.du.txt | csvtk tab2csv | csvtk add-header -n size,file > ${sampleName}.du_stats.csv
 
 
@@ -32,10 +32,10 @@ process UTILS_FASTQ_STATS {
 
         """
 
-    stub: 
+    stub:
 
         """
-        touch ${sampleName}.check.tsv 
-        """ 
+        touch ${sampleName}.check.tsv
+        """
 
 }
diff --git a/workflows/validate_fastqs_wf.nf b/workflows/validate_fastqs_wf.nf
@@ -48,9 +48,9 @@ workflow VALIDATE_FASTQS_WF {
 
         FASTQ_VALIDATOR( reads_ch, ready )
 
-        UTILS_FASTQ_STATS( FASTQ_VALIDATOR.out.passed_reads )
+        UTILS_FASTQ_STATS( FASTQ_VALIDATOR.out.reads )
 
-        UTILS_FASTQ_COHORT_VALIDATION( FASTQ_VALIDATOR.out.check_result.collect() )
+        UTILS_FASTQ_COHORT_VALIDATION( FASTQ_VALIDATOR.out.check_result.collect(), UTILS_FASTQ_STATS.out.collect() )
 
     emit: